search

gcr / torch-residual-networks

This is a Torch implementation of ["Deep Residual Learning for Image Recognition",Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun](http://arxiv.org/abs/1512.03385) the winners of the 2015 ILSVRC and COCO challenges.
zlib License
576 stars 145 forks source link

Classification with pre-loaded model problems #13

Open leonardoaraujosantos opened 8 years ago

leonardoaraujosantos commented 8 years ago

Hi Guys I'm trying to classify images with the pre-loaded models but something is strange....

$ th classify.lua resnet-34.t7 ImgnetCat.jpg Classes for ImgnetCat.jpg
0.0075856610201299 bucket, pail
0.0070607061497867 hook, claw
0.0061263972893357 water bottle
0.0054563735611737 tennis ball 0.0046155038289726 plastic bag

$ th classify.lua resnet-34.t7 Tennis-ball-007.jpg 0.0085550472140312 bucket, pail
0.0073438654653728 hook, claw
0.0070917885750532 water bottle
0.0054101385176182 water jug
0.0049047190696001 sunglasses, dark glasses, shades

I'm doing something wrong? Thanks

I'm using the following images tennis-ball-007 imgnetcat